Related papers: Discriminator Augmented Model-Based Reinforcement …
Estimates of predictive uncertainty are important for accurate model-based planning and reinforcement learning. However, predictive uncertainties---especially ones derived from modern deep learning systems---can be inaccurate and impose a…
This paper explores multiple optimization methods to improve the performance of rating-based reinforcement learning (RbRL). RbRL, a method based on the idea of human ratings, has been developed to infer reward functions in reward-free…
Sampling-based motion planning is a well-established approach in autonomous driving, valued for its modularity and analytical tractability. In complex urban scenarios, however, uniform or heuristic sampling often produces many infeasible or…
Hierarchical model-based reinforcement learning (HMBRL) aims to combine the benefits of better sample efficiency of model based reinforcement learning (MBRL) with the abstraction capability of hierarchical reinforcement learning (HRL) to…
Reinforcement learning is able to solve complex sequential decision-making tasks but is currently limited by sample efficiency and required computation. To improve sample efficiency, recent work focuses on model-based RL which interleaves…
Model-based reinforcement learning (MBRL) allows solving complex tasks in a sample-efficient manner. However, no information is reused between the tasks. In this work, we propose a meta-learned addressing model called RAMa that provides…
Standard model-based reinforcement learning (MBRL) approaches fit a transition model of the environment to all past experience, but this wastes model capacity on data that is irrelevant for policy improvement. We instead propose a new…
For autonomous vehicles integrating onto roadways with human traffic participants, it requires understanding and adapting to the participants' intention and driving styles by responding in predictable ways without explicit communication.…
Offline inverse reinforcement learning (Offline IRL) aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent. Accurate models of…
We introduce a Bayesian (deep) model-based reinforcement learning method (RoMBRL) that can capture model uncertainty to achieve sample-efficient policy optimisation. We propose to formulate the model-based policy optimisation problem as a…
There is growing interest in reinforcement learning (RL) methods that leverage the simulator's derivatives to improve learning efficiency. While early gradient-based approaches have demonstrated superior performance compared to…
In model-based reinforcement learning, the agent interleaves between model learning and planning. These two components are inextricably intertwined. If the model is not able to provide sensible long-term prediction, the executed planner…
Model-based offline reinforcement learning (RL) aims to find highly rewarding policy, by leveraging a previously collected static dataset and a dynamics model. While the dynamics model learned through reuse of the static dataset, its…
Reinforcement Learning (RL) is a potent tool for sequential decision-making and has achieved performance surpassing human capabilities across many challenging real-world tasks. As the extension of RL in the multi-agent system domain,…
Although reinforcement learning has seen tremendous success recently, this kind of trial-and-error learning can be impractical or inefficient in complex environments. The use of demonstrations, on the other hand, enables agents to benefit…
Model-based reinforcement learning attempts to use an available or learned model to improve the data efficiency of reinforcement learning. This work proposes a one-step lookback approach that jointly learns the deep incremental model and…
Deep reinforcement learning (DRL) has achieved groundbreaking successes in a wide variety of robotic applications. A natural consequence is the adoption of this paradigm for safety-critical tasks, where human safety and expensive hardware…
Recently, there has been increasing interest in transparency and interpretability in Deep Reinforcement Learning (DRL) systems. Verbal explanations, as the most natural way of communication in our daily life, deserve more attention, since…
Model-based reinforcement learning has the potential to be more sample efficient than model-free approaches. However, existing model-based methods are vulnerable to model bias, which leads to poor generalization and asymptotic performance…
The development of autonomous web agents, powered by Large Language Models (LLMs) and reinforcement learning (RL), represents a significant step towards general-purpose AI assistants. However, training these agents is severely hampered by…